DreamForge-World 0.1 Preview: A Low-Compute Real-Time Controllable World Model
2026-06-29 • Machine Learning
Machine LearningComputer Vision and Pattern Recognition
AI summaryⓘ
The authors introduce DreamForge-World 0.1 Preview, a system that simulates interactive virtual worlds in real time using less powerful hardware like typical consumer GPUs. They built it by adapting existing video generation models with new features for user control, such as keyboard and mouse input and changing commands during simulation. Although this version is not yet advanced enough to remember everything perfectly or match top-tier simulators, it demonstrates a cost-effective way to run interactive world models smoothly at a moderate video quality on widely available hardware.
world modelautoregressive videoconsumer GPUinteractive simulationmultimodal initializationreal-time controlresidual action pathwayvideo backboneRTX 4090low memory footprint
Authors
Daniyel Ayupov, Artur Markov-Tsoy
Abstract
We present DreamForge-World 0.1 Preview, a preview foundational world model for real-time interactive world simulation. The system adapts the LongLive 1 autoregressive video stack, itself derived from Wan2.1-T2V-1.3B, with a residual action pathway inspired by the Matrix-Game family. DreamForge-World 0.1 Preview focuses on a complementary axis to frontier-scale world simulators: low-compute adaptation, consumer-GPU runtime, and broad interactive capability coverage. It supports live keyboard and mouse control, multimodal initialization, mid-stream reprompting, dual-view operation, and minute-scale interactive rollouts at native 480p resolution, reaching up to 14 to 15 FPS FPS on a single RTX 4090 with a low memory footprint. By leveraging open video backbones and applying targeted adaptation runs, we build the preview system with high cost-efficiency. DF-World 0.1 Preview is not yet a memory-complete or frontier-quality world simulator, but demonstrates a practical low-compute route toward real-time controllable world-model previews on consumer GPUs.